The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and configuration metadata. There are no executable scripts, binaries, or tool invocations that perform operations on the host system.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external files such as .agents/marketing-context.md and process user-provided research data (surveys, interviews). While this creates a surface for indirect prompt injection, the skill lacks the capabilities (network access, file-writing, or system commands) to translate such an injection into a technical compromise. The risk is limited to the accuracy of the generated pricing recommendation.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration patterns were detected. The skill operates on provided business context to generate strategies.

pricing